Advertisement

Representation Sharing for Fast Object Detector Search and Beyond

Conference paper
  • 585 Downloads
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12364)

Abstract

Region Proposal Network (RPN) provides strong support for handling the scale variation of objects in two-stage object detection. For one-stage detectors which do not have RPN, it is more demanding to have powerful sub-networks capable of directly capturing objects of unknown sizes. To enhance such capability, we propose an extremely efficient neural architecture search method, named Fast And Diverse (FAD), to better explore the optimal configuration of receptive fields and convolution types in the sub-networks for one-stage detectors. FAD consists of a designed search space and an efficient architecture search algorithm. The search space contains a rich set of diverse transformations designed specifically for object detection. To cope with the designed search space, a novel search algorithm termed Representation Sharing (RepShare) is proposed to effectively identify the best combinations of the defined transformations. In our experiments, FAD obtains prominent improvements on two types of one-stage detectors with various backbones. In particular, our FAD detector achieves 46.4 AP on MS-COCO (under single-scale testing), outperforming the state-of-the-art detectors, including the most recent NAS-based detectors, Auto-FPN  [42] (searched for 16 GPU-days) and NAS-FCOS  [39] (28 GPU-days), while significantly reduces the search cost to 0.6 GPU-days. Beyond object detection, we further demonstrate the generality of FAD on the more challenging instance segmentation, and expect it to benefit more tasks.

Supplementary material

504475_1_En_28_MOESM1_ESM.pdf (225 kb)
Supplementary material 1 (pdf 225 KB)

References

  1. 1.
    Chen, Y., Yang, T., Zhang, X., Meng, G., Pan, C., Sun, J.: DetNAS: backbone search for object detection. arXiv preprint arXiv:1903.10979 (2019)
  2. 2.
    Dai, J., Li, Y., He, K., Sun, J.: R-FCN: object detection via region-based fully convolutional networks. In: Advances in Neural Information Processing Systems, pp. 379–387 (2016)Google Scholar
  3. 3.
    Dai, J., et al.: Deformable convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 764–773 (2017)Google Scholar
  4. 4.
    Duan, K., Bai, S., Xie, L., Qi, H., Huang, Q., Tian, Q.: CenterNet: keypoint triplets for object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 6569–6578 (2019)Google Scholar
  5. 5.
    Everingham, M., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge. Int. J. Comput. Vis. 88(2), 303–338 (2010).  https://doi.org/10.1007/s11263-009-0275-4CrossRefGoogle Scholar
  6. 6.
    Ghiasi, G., Lin, T.Y., Le, Q.V.: DropBlock: a regularization method for convolutional networks. In: Advances in Neural Information Processing Systems, pp. 10727–10737 (2018)Google Scholar
  7. 7.
    Ghiasi, G., Lin, T.Y., Le, Q.V.: NAS-FPN: learning scalable feature pyramid architecture for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7036–7045 (2019)Google Scholar
  8. 8.
    Goldberg, D.E., Deb, K.: A comparative analysis of selection schemes used in genetic algorithms. In: Foundations of Genetic Algorithms, vol. 1, pp. 69–93. Elsevier (1991)Google Scholar
  9. 9.
    Guo, J., et al.: Hit-detector: hierarchical trinity architecture search for object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 11405–11414 (2020)Google Scholar
  10. 10.
    He, K., Gkioxari, G., Dollár, P., Girshick, R.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961–2969 (2017)Google Scholar
  11. 11.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)Google Scholar
  12. 12.
    Howard, A.G., et al.: MobileNets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)
  13. 13.
    Huang, Z., Huang, L., Gong, Y., Huang, C., Wang, X.: Mask scoring R-CNN. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6409–6418 (2019)Google Scholar
  14. 14.
    Law, H., Deng, J.: CornerNet: detecting objects as paired keypoints. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision – ECCV 2018. LNCS, vol. 11218, pp. 765–781. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01264-9_45CrossRefGoogle Scholar
  15. 15.
    Li, Y., Chen, Y., Wang, N., Zhang, Z.: Scale-aware trident networks for object detection. arXiv preprint arXiv:1901.01892 (2019)
  16. 16.
    Liang, F., et al.: Computation reallocation for object detection. arXiv preprint arXiv:1912.11234 (2019)
  17. 17.
    Lin, T.Y., Dollár, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117–2125 (2017)Google Scholar
  18. 18.
    Lin, T.Y., Goyal, P., Girshick, R., He, K., Dollár, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980–2988 (2017)Google Scholar
  19. 19.
    Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740–755. Springer, Cham (2014).  https://doi.org/10.1007/978-3-319-10602-1_48CrossRefGoogle Scholar
  20. 20.
    Liu, C., et al.: Auto-DeepLab: hierarchical neural architecture search for semantic image segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 82–92 (2019)Google Scholar
  21. 21.
    Liu, C., et al.: Progressive neural architecture search. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11205, pp. 19–35. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01246-5_2CrossRefGoogle Scholar
  22. 22.
    Liu, H., Simonyan, K., Yang, Y.: DARTS: differentiable architecture search. arXiv preprint arXiv:1806.09055 (2018)
  23. 23.
    Liu, S., Huang, D., Wang, Y.: Receptive field block net for accurate and fast object detection. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11215, pp. 404–419. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01252-6_24CrossRefGoogle Scholar
  24. 24.
    Liu, W., et al.: SSD: single shot MultiBox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21–37. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46448-0_2CrossRefGoogle Scholar
  25. 25.
    Luo, R., Tian, F., Qin, T., Chen, E., Liu, T.Y.: Neural architecture optimization. In: Advances in Neural Information Processing Systems, pp. 7816–7827 (2018)Google Scholar
  26. 26.
    Peng, J., Sun, M., Zhang, Z., Tan, T., Yan, J.: Efficient neural architecture transformation searchin channel-level for object detection. arXiv preprint arXiv:1909.02293 (2019)
  27. 27.
    Pham, H., Guan, M.Y., Zoph, B., Le, Q.V., Dean, J.: Efficient neural architecture search via parameter sharing. arXiv preprint arXiv:1802.03268 (2018)
  28. 28.
    Real, E., Aggarwal, A., Huang, Y., Le, Q.V.: Regularized evolution for image classifier architecture search. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 4780–4789 (2019)Google Scholar
  29. 29.
    Real, E., et al.: Large-scale evolution of image classifiers. In: Proceedings of the 34th International Conference on Machine Learning-Volume 70, pp. 2902–2911. JMLR. org (2017)Google Scholar
  30. 30.
    Redmon, J., Farhadi, A.: YOLOv3: an incremental improvement. arXiv preprint arXiv:1804.02767 (2018)
  31. 31.
    Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91–99 (2015)Google Scholar
  32. 32.
    Sifre, L., Mallat, S.: Rigid-motion scattering for image classification. Ph.D. dissertation (2014)Google Scholar
  33. 33.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
  34. 34.
    Singh, B., Davis, L.S.: An analysis of scale invariance in object detection SNIP. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3578–3587 (2018)Google Scholar
  35. 35.
    Singh, B., Najibi, M., Davis, L.S.: SNIPER: efficient multi-scale training. In: Advances in Neural Information Processing Systems, pp. 9310–9320 (2018)Google Scholar
  36. 36.
    Stamoulis, D., et al.: Single-Path NAS: designing hardware-efficient convnets in less than 4 hours. arXiv preprint arXiv:1904.02877 (2019)
  37. 37.
    Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–9 (2015)Google Scholar
  38. 38.
    Tian, Z., Shen, C., Chen, H., He, T.: FCOS: fully convolutional one-stage object detection. arXiv preprint arXiv:1904.01355 (2019)
  39. 39.
    Wang, N., Gao, Y., Chen, H., Wang, P., Tian, Z., Shen, C.: NAS-FCOS: fast neural architecture search for object detection. arXiv preprint arXiv:1906.04423 (2019)
  40. 40.
    Wu, Y., He, K.: Group normalization. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11217, pp. 3–19. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01261-8_1CrossRefGoogle Scholar
  41. 41.
    Xie, S., Girshick, R., Dollár, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks (2017)Google Scholar
  42. 42.
    Xu, H., Yao, L., Zhang, W., Liang, X., Li, Z.: Auto-FPN: automatic network architecture adaptation for object detection beyond classification. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 6649–6658 (2019)Google Scholar
  43. 43.
    Yao, L., Xu, H., Zhang, W., Liang, X., Li, Z.: SM-NAS: structural-to-modular neural architecture search for object detection. arXiv preprint arXiv:1911.09929 (2019)
  44. 44.
    Zhang, S., Chi, C., Yao, Y., Lei, Z., Li, S.Z.: Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9759–9768 (2020)Google Scholar
  45. 45.
    Zhang, X., Wan, F., Liu, C., Ji, R., Ye, Q.: FreeAnchor: learning to match anchors for visual object detection. In: Advances in Neural Information Processing Systems, pp. 147–155 (2019)Google Scholar
  46. 46.
    Zhu, C., Chen, F., Shen, Z., Savvides, M.: Soft anchor-point object detection. arXiv preprint arXiv:1911.12448 (2019)
  47. 47.
    Zhu, C., He, Y., Savvides, M.: Feature selective anchor-free module for single-shot object detection. arXiv preprint arXiv:1903.00621 (2019)
  48. 48.
    Zoph, B., Le, Q.V.: Neural architecture search with reinforcement learning. arXiv preprint arXiv:1611.01578 (2016)

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Malong LLCWilmingtonUSA

Personalised recommendations